context-validate

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for the legitimate purpose of validating project documentation structure and quality.
  • [COMMAND_EXECUTION]: The skill uses a local shell command ('pnpm lint:md') to execute a markdown linter on repository files. This is a standard development task and does not involve downloading external scripts or reaching out to untrusted remote sources.
  • [PROMPT_INJECTION]: The skill reads external project documentation ('CLAUDE.md' files). While this presents a theoretical attack surface where an agent could ingest instructions from documentation, the skill is focused on validation and linting, which is a low-risk operation in this context.
  • [DATA_EXFILTRATION]: The skill accesses project-specific configuration files ('.claude/design/design.config.json') to retrieve quality standards. This access is scoped to the local development environment and does not involve sending data to external or untrusted servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:05 AM
Security Audit — agent-trust-hub — context-validate